Port City International University

The high cost of expert annotations significantly hinders the advancement of deep learning models for clinical medical imaging. This work introduces an efficient entropy-based active learning framework that achieves outstanding classification performance for renal abnormalities (Normal, Cyst, Stone, Tumor) in CT scans while requiring only a minimal amount of labeled data. The dataset comprises 12,446 CT slices split 70/15/15 into training (8,716), validation (1,865), and test (1,865) partitions via stratified sampling. Starting with only 200 randomly selected images and employing predictive entropy for uncertainty sampling on a pretrained ResNet-50 backbone, the proposed method attains 99.71% ± 0.25% mean test accuracy (95% CI: [99.30, 99.94]) across five independent runs after just six query cycles on the standard 12,446-image CT kidney dataset. Our method uses only 2,000 labeled training images, representing 22.9% of the 8,716-image training partition (a 77.1% reduction in required annotations relative to full supervision of the training set). This performance matches or exceeds prior fully supervised methods trained on the complete labeled training partition while demonstrating substantially improved sample efficiency, particularly in early annotation cycles where entropy-guided selection converges significantly faster than random sampling. Statistical testing across five repeated runs confirms that results are stable (Shapiro-Wilk p = 0.148). The framework exhibits exceptional sample efficiency as described by an empirically fitted power-law curve with a fitted exponent of 1.2, and empirically observed uncertainty decay with a rate of 0.92. These results offer both practical insights into annotation efficiency and substantial application value in the medical imaging domain.

This present study aims to investigate the influence of board characteristics on the level of climate change disclosures and the extent to which the implementation of the corporate governance code (CGC) moderates these factors. The ordinary least squares statistical method is used to analyze the panel data. In addition, the Tobit regression model is also estimated to check the robustness of the study findings. This study suggests that larger board sizes, more independent directors, and board meeting frequency are positively associated with higher levels of climate change disclosure. However, the study does not find any association between CEO duality, foreign ownership, and climate change disclosure. In addition, it is also observed that CGC can enhance the influence of board characteristics on the likelihood of disclosing climate information. The study offers necessary directions for regulatory authorities, business firms, and practitioners to be more transparent in disclosing climate information and extends guidelines to tackle climate change disclosure issues.

Customers' reviews are laden with emotions and therefore present a challenge from data analytical perspectives. When looking at more than three data categories, this analysis becomes even more complicated. The English language does have access to a wide variety of data and advanced pre-trained models. However, the same cannot be said for the Bangla language, which does not have large documented datasets nor accurate methods of data labelling due to being a low-resource language. The goal of this study is to fulfil this gap by proposing a novel model for the classification of Bangla reviews into the following five categories concerning emotions: Negative(0), Positive(1), Neutral(2), Slightly Negative(3), and Slightly Positive(4). 26,028 Bangla reviews were collected from famous e-commerce platforms, annotated by 3 annotators. Inter-annotator reliability was strong (Cohen's $\kappa=0.81$; Fleiss' $\kappa=0.79)$ and processed through a Bangla-focused normalization, which included language filtering, script correction, tokenization, removal of stop-words, and light morphological reduction. Classical TF-IDF features and transformer-based subword embeddings used to represent the text. Six classical ML algorithms (MNB, LR, SVM, RF, KNN, and Decision Tree) and three transformer models (BanglaBERT, RoBERTa, Sentence-BERT) were evaluated under the same setup. Among all models, SVM and Random Forest reached highest 95% accuracy, while RoBERTa achieved 84%. Model outcomes indicate that, even with modern architectures available, optimized classical models still offer strong performance. For evaluation transparency, we report also precision, recall, and F 1, and we describe an additional robustness protocol beyond a single random split to reduce the risk of split-dependent conclusions.

Early-stage and accurate detection of plant diseases is critical for maximizing crop productivity and enabling sustainable agricultural systems. This study proposes an efficient deep learning framework for the automated identification of diseases in bell pepper foliage. The approach utilizes three different architectures, namely CNN, ResNet-18, and EfficientNet-B0, to perform classification. To improve the interpretability of the model and offer visual insights into its predictions, the Gradient-weighted Class Activation Mapping++ (Grad-CAM++) technique is utilized as an Explainable Artificial Intelligence (XAI) approach. The technique highlights the most critical regions within leaf images that contribute to the model's decision-making process. Experimental evaluations reveal that ResNet-18 and EfficientNet-B0 outperform the conventional CNN model, attaining precision, recall, and F1-score values of 0.99, while successfully capturing fine-grained visual features associated with infected regions. The contribution of this work lies in the seamless integration of advanced deep learning architectures with XAI-enabled interpretability, offering both high accuracy and explainability which is a critical factor for real-world agricultural applications. Using The key visual cues behind each prediction, the proposed framework not only provides reliable disease detection but also empower farmers and agronomists useful information. Potentially transforming precision agriculture practices by this method, field-deployable, and this approach paves the way for real-time plant disease diagnostic systems.

Nitrogen containing flame retardants are the most commonly used flame retardants for textile materials. In the case of eco-friendly flame retardant textiles, it is better to utilize nitrogen-based natural flame retardants. In this study, aloe vera, bean seed, and tea leaf solutions were coated on 100